🔎 Evidence browser

Browse the skill radar

Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · browser-and-automation

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.

🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got.

📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.

⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.

🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.

Results

Showing 24 of 320 skills in the browsable catalog view · reviewed: no · category: browser-and-automation · sort: score

page evidence snapshotruntime-passed: 0 runtime-failed: 0 source-scanned: 22 fresh <24h: 0 manual review: 0

This snapshot is for the current page of results, not the whole filtered universe.

Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.

interesting-finding

zerone0x · vsource-scanned

Process links and content shared in the #interesting-finding Discord channel. Use when: (1) a URL or article is shared in #interesting-finding, (2) someone asks to log or analyze content from #interesting-finding, (3) performing a heartbeat check and #interesting-finding has new unread content. Workflow: fetch URL → analyze → create Discord thread → post summary to thread → save distilled notes to knowledge base (memory/kb/).

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

market-test-price

li-zoe-x · vsource-scanned

>

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

naverstock-skill

seungdols · vsource-scanned

Fetch text-based real-time stock prices (KRX, Overseas) using Naver Finance.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (trading), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

nblm

magicseek · vsource-scanned

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

nova-act

zouchaoqun · vsource-scanned

Write and execute Python scripts using Amazon Nova Act for AI-powered browser automation tasks like flight searches, data extraction, and form filling.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

powerdrill-data-analysis-skill

javainthinking · vsource-scanned

This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like "analyze my data", "query my dataset", "upload this file for analysis", "list my datasets", "create a dataset", "visualize sales trends", "continue my previous analysis", "delete this dataset", or any data exploration task mentioning Powerdrill.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

powerdrill-skills

javainthinking · vsource-scanned

This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like "analyze my data", "query my dataset", "upload this file for analysis", "list my datasets", "create a dataset", "visualize sales trends", "continue my previous analysis", "delete this dataset", or any data exploration task mentioning Powerdrill.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

sota-tracker-mcp

romancircus · vsource-scanned

**The definitive open-source database of State-of-the-Art AI models.**

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

tushare-base

wdblink · vsource-scanned

Fetch Chinese stock and futures market data via Tushare API. Supports stock quotes, futures data, company fundamentals, and macroeconomic indicators. Use when the user needs financial data from Chinese markets. Requires TUSHARE_TOKEN environment variable.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (trading, token, email), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

x-bookmarks

sharbelayy · vsource-scanned

>

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (trading, token, oauth), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ai-news-oracle

swimmingkiim · vsource-scanned

Fetch real-time AI news briefings from the AI News Oracle API (Hacker News, TechCrunch, The Verge). Uses a10m.work registry for discovery and Paymaster for gasless transactions.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

hive-mind

lilyjazz · vsource-scanned

Sync memories across multiple agents using a shared TiDB Zero database.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

input-classification-v1

omprasad122007-rgb · vsource-scanned

Deterministic rule-based system for classifying clarified input into a single primary task category and assigning execution complexity. Use when the Main Agent needs to categorize user requests before task decomposition, route tasks to appropriate handlers, assess complexity and risk levels, or determine if clarification is needed. Triggers after clarification is complete and before decomposition begins.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

linux-desktop

ouyangabel · vsource-scanned

Linux desktop automation and control. Use when: (1) taking screenshots of the screen or windows, (2) controlling mouse and keyboard, (3) managing windows, (4) automating desktop tasks, or (5) any Linux desktop interaction needs. Supports screenshot capture, mouse movement, typing, and window management.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

nba-data-analytics

project-aeris-disaster-agent · vsource-scanned

Use this skill in two ways:

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

nso-macro-monitor

ndtchan · vsource-scanned

Monitors official Vietnam NSO monthly and quarterly socio-economic releases and compares same-period trends; used when users request official macro updates and year-over-year context.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

paper-notion-summarizer

lococaeco · vsource-scanned

Fetch paper metadata by title or arXiv/DOI link, create a deep structured summary, and post it as a Notion page. The agent reads the paper and writes a seminar-quality summary adapted to the user's language.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

xdotool-control

jeremysommerfeld8910-cpu · vsource-scanned

Mouse and keyboard automation using xdotool. Use when clicking Chrome extension icons, typing into GUI apps, switching browser tabs, automating desktop UI, or running screenshot-verify-click loops without a browser relay. Triggers on: 'click extension icon', 'click coordinates', 'type in window', 'switch tab', 'automate mouse', 'screenshot and click', 'xdotool', 'desktop automation', 'GUI automation without relay'.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

adcp-advertising

edyyy62 · vsource-scanned

Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and performance tracking. Launch Facebook ads, Google ads, display advertising, video marketing, and multi-channel campaigns using natural language. Supports ad targeting, audience segmentation, ROI tracking, and automated bidding.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token, oauth), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

browsh

gumadeiras · vsource-scanned

A modern text-based browser. Renders web pages in the terminal using headless Firefox.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cn-ecommerce-search

shopmeskills · vsource-scanned

>

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

coda-io

simonfunk · vsource-scanned

>

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token, email), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

code-tester

frhn9 · vcatalog

Build, run, and test code projects for Rust, Go, and Java.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

glm-image

chunhualiao · vcatalog

Generate images using GLM-Image API.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

« First ← Prev 1 7 8 9 14Page 8 / 14Next →Last »